A transformer winding insulation monitoring system

Abstract

The present invention belongs to the technical field of winding insulation monitoring, and discloses a transformer winding insulation monitoring system, comprising: collecting transformer winding data and aging degree labels; performing image enhancement processing, temperature correction, hot spot detection and temperature marking on the transformer winding data to generate a hot spot temperature distribution map; constructing a winding insulation aging prediction model for predicting the winding insulation aging degree based on the hot spot temperature distribution map and the aging degree labels; collecting real-time transformer winding data, making predictions based on the real-time transformer winding data through the winding insulation aging prediction model to obtain the winding insulation aging degree, and making early warning judgments based on the winding insulation aging degree; greatly improving the initiative of transformer maintenance, helping users take necessary measures before a fault occurs, reducing the risk of power outages and equipment damage, and extending the service life of the equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of winding insulation monitoring, and more particularly to a transformer winding insulation monitoring system. Background Art

[0002] The patent application publication number CN112710929A discloses a power electronic transformer winding interlayer

[0003] An insulation monitoring method and system are provided. Before using a power electronic transformer, a swept common-mode voltage excitation is applied, and the ratio of the common-mode component amplitudes is used as a health state transfer function. A curve of the health state transfer function changing with frequency is obtained, and the effective frequency band for monitoring interlayer insulation is clearly defined. After use, when it is necessary to monitor interlayer insulation, the harmonic components of the output voltage of the power electronic transformer are adjusted so as to cover the effective frequency band. The voltages at the winding entry point and the neutral point are measured online, and the common-mode components of the two are calculated to obtain an online curve of the transfer function changing with frequency. The online curve of the transfer function changing with frequency is compared with the curve of the health state transfer function changing with frequency to determine the insulation state between the winding layers of the power electronic transformer. By controlling the converter switch modulation strategy for a power electronic transformer with a multi-layer winding structure, online monitoring of the insulation between the winding layers of the power electronic transformer is achieved.

[0004] Under long-term operation, the insulation materials of transformer windings are prone to thermal aging in high-temperature environments, resulting in a decrease in insulation performance. The chemical structure of materials such as insulating paper and oil may change, reducing their dielectric strength. Under existing technologies, the aging problem of transformer winding insulation is solved through regular maintenance methods, which cannot be detected in real time, resulting in low reliability and stability of the power system.

[0005] In view of this, the present invention proposes a transformer winding insulation monitoring system to solve the above problem. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solutions: A transformer winding insulation monitoring system comprises: a data acquisition module: collecting transformer winding data and aging degree labels;

[0007] Data processing module: Performs image enhancement processing on transformer winding data to generate enhanced winding image data, performs temperature conversion processing based on the enhanced winding image data, performs temperature correction based on the ambient temperature, and generates actual temperature data; performs hotspot detection and temperature marking based on the actual temperature data to generate a hotspot temperature distribution map;

[0008] Model building module: Builds a winding insulation aging prediction model based on the hotspot temperature distribution map and aging degree labels to predict the degree of winding insulation aging;

[0009] Real-time detection module: collects real-time transformer winding data, predicts the degree of winding insulation aging based on the real-time transformer winding data through the winding insulation aging prediction model, obtains the degree of winding insulation aging, and makes early warning judgments based on the degree of winding insulation aging.

[0010] Furthermore, the transformer winding data includes: winding thermal image and ambient temperature; aging degree labels include: normal, slightly aged, moderately aged and severely aged.

[0011] Furthermore, the method of performing image enhancement processing on the transformer winding data includes:

[0012] The upper left corner of the winding thermal image is used as the coordinate origin, and the number of pixels of the length and width of the winding thermal image is used as the coordinate axis scale to construct a pixel coordinate system. Based on the pixel coordinate system, a preset length of , width is The winding thermal image is smoothed based on the pixel neighborhood and the smoothing formula is:

[0013] ;in, Represents the coordinates in the pixel coordinate system The smoothed pixel value of the pixel at Represents the horizontal axis value of the pixel coordinate system, Represents the vertical axis value of the pixel coordinate system, represents the length of the pixel neighborhood, represents the width of the pixel neighborhood, Represents the coordinates in the pixel coordinate system The pixel value of the pixel at Represents the standard deviation of the pixel values ​​in the winding thermal image, represents pi;

[0014] The winding thermal image is regionally enhanced based on the smoothed pixel value. The calculation formula for regional enhancement is: ;in, Represents the coordinates in the pixel coordinate system The enhanced pixel value of the pixel at Represents the coordinates in the pixel coordinate system The second-order derivative of the pixel point in the horizontal direction of the pixel coordinate system, Represents the coordinates in the pixel coordinate system The second-order derivative of the pixel point in the vertical direction of the pixel coordinate system.

[0015] Furthermore, the method of generating actual temperature data includes:

[0016] Temperature conversion based on enhanced pixel value, formula for temperature conversion

[0017] ;in, Represents the coordinates in the pixel coordinate system The pixel temperature of the pixel at and represents the calibration constant, represents the material emissivity;

[0018] The pixel temperature is corrected based on the ambient temperature. The temperature correction formula is:

[0019] ;in, Represents the coordinates in the pixel coordinate system The actual temperature of the pixel at Represents the ambient temperature.

[0020] Furthermore, the method of generating the hotspot temperature distribution map includes:

[0021] The temperature threshold is preset, and hotspot detection is performed on the actual temperature based on the temperature threshold. The formula for hotspot detection is: ;in, Represents the hotspot labeling matrix, 1 represents a hotspot, 0 represents a non-hotspot, represents the temperature threshold;

[0022] Based on the hotspot marking matrix, the hotspot temperature of the winding thermal image is marked to obtain the hotspot temperature distribution map. The formula for hotspot temperature marking is: ;in, Represents the coordinates in the pixel coordinate system The temperature value of the pixel.

[0023] Furthermore, the winding insulation aging prediction model is constructed in the following manner:

[0024] The winding insulation aging prediction model is defined, and the defined winding insulation aging prediction model is trained and tuned through the optimization algorithm to obtain the optimal winding insulation aging prediction model.

[0025] Furthermore, the method of defining the model includes:

[0026] The winding insulation aging prediction model is a neural network model. It uses the hotspot temperature distribution map as input, the winding insulation aging degree as output, and the aging degree label as the prediction target for model training. The architecture of the winding insulation aging prediction model includes: convolution layer, pooling layer, and fully connected layer. The formula for defining the convolution operation of the winding insulation aging prediction model is: ;in, Representative The convolution kernel is located at the hotspot temperature distribution map. The convolution value at Represents the index of the long side pixel of the hotspot temperature distribution map, Represents the index of the wide edge pixel of the hotspot temperature distribution map, represents the index of the convolution kernel, Representative The weight matrix of the convolution kernel, and represents the index of the element position in the weight matrix, The representative hot spot temperature distribution diagram is at position The pixel value at Representative The bias term of the convolution kernel, represents the activation function;

[0027] The loss function of the winding insulation aging prediction model is defined as: ;in, represents the loss function value, Represents the total number of aging degree label categories, Represents the aging degree label category index, Represents the true distribution The probability of an aging degree label, Represents the first The probability of an aging degree label.

[0028] Furthermore, the step of performing training and tuning includes:

[0029] Step 1: Initialize E ants; initialize the parameter space of the winding insulation aging prediction model, which includes the weight matrix and bias term of the convolution kernel, and assign each ant to a different position in the parameter space; initialize pheromone: assign an initial pheromone concentration to each ant;

[0030] Step 2: Each ant moves in the parameter space and selects the direction of the next position to be updated based on the path probability. The calculation formula of the path probability is: ;in, Represents the ant from the position Select Path to Location The probability of Representative position To location The pheromone concentration, Pheromone weight coefficient, and represents the position index, and , Representative position The inverse of the loss function value of the winding insulation aging prediction model in the corresponding parameter space, The index representing the selected position;

[0031] Step 3: After each ant selects a path, it updates its position and calculates the loss function value corresponding to each ant based on the parameters at the selected position through the loss function of the winding insulation aging prediction model;

[0032] Step 4: Update the pheromone concentration of the found path according to the loss function value corresponding to each ant. The formula for updating the pheromone concentration is:

[0033] ;in, Representative position To location The updated value of the pheromone concentration, represents the pheromone volatility coefficient, represents the index of the ant, Representative The loss function value of an ant, represents the total number of ants, represents a constant;

[0034] Step 5: When the maximum number of iterations is reached or the loss function of the winding insulation aging prediction model converges, the parameters corresponding to the locations where the largest number of ants gather are the parameter space that minimizes the loss function value of the winding insulation aging prediction model. When the maximum number of iterations is not reached and the loss function of the winding insulation aging prediction model has not converged, repeat steps 2, 3, and 4.

[0035] Furthermore, the method of performing early warning judgment according to the degree of winding insulation aging includes:

[0036] Collect real-time transformer winding data, including real-time winding thermal images and real-time ambient temperature. Process the real-time transformer winding data accordingly to obtain a hotspot temperature distribution map. Use the hotspot temperature distribution map as input for the winding insulation aging prediction model to predict the degree of winding insulation aging. Activate an alarm when the winding insulation aging degree is moderate or severe.

[0037] The technical effects and advantages of the transformer winding insulation monitoring system of the present invention are as follows:

[0038] By performing hotspot detection and temperature marking on transformer winding data, the present invention can better demonstrate the local temperature changes of the winding, effectively identify abnormal hotspot areas, improve the accuracy of hotspot detection, and ensure the reliability and accuracy of detection; through the neural network model, accurate prediction of the degree of aging of the winding insulation is achieved, and the adaptability and prediction accuracy of the system in different environments are improved; through the ant colony algorithm to optimize the model parameters, the intelligent search mechanism of the biological population is simulated, the convergence speed and optimization effect of the model are improved, thereby effectively improving the prediction accuracy of the model; by accurately predicting the aging degree of the transformer winding, the initiative of transformer maintenance is greatly improved, helping users take necessary measures before a fault occurs, reducing the risk of power outages and equipment damage, and extending the service life of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A schematic diagram of a transformer winding insulation monitoring system according to the present invention;

[0040] Figure 2 Schematic diagram of a transformer winding insulation monitoring method according to the present invention. DETAILED DESCRIPTION

[0041] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0042] Example 1

[0043] See also Figure 1 As shown, the transformer winding insulation monitoring system described in this embodiment includes: a data acquisition module: collecting transformer winding data and aging degree labels;

[0044] Data processing module: Performs image enhancement processing on transformer winding data to generate enhanced winding image data, performs temperature conversion processing based on the enhanced winding image data, performs temperature correction based on the ambient temperature, and generates actual temperature data; performs hotspot detection and temperature marking based on the actual temperature data to generate a hotspot temperature distribution map;

[0045] Model building module: Builds a winding insulation aging prediction model based on the hotspot temperature distribution map and aging degree labels to predict the degree of winding insulation aging;

[0046] Real-time detection module: collects real-time transformer winding data, uses the winding insulation aging prediction model to predict the degree of winding insulation aging based on the real-time transformer winding data, and makes early warning judgments based on the degree of winding insulation aging;

[0047] Each module is connected via wired and / or wireless means to achieve data transmission between modules;

[0048] Transformer winding data includes: winding thermal images and ambient temperature; aging degree labels are obtained through manual judgment by experts, and aging degree labels include: normal, slightly aged, moderately aged, and severely aged. The use of expert aging degree labels makes the data source more accurate and targeted;

[0049] The winding thermal image is obtained by scanning the transformer winding insulation with a high-precision infrared thermal imager, and the ambient temperature is obtained with a temperature measuring instrument;

[0050] The upper left corner of the winding thermal image is used as the coordinate origin, and the number of pixels of the length and width of the winding thermal image is used as the coordinate axis scale to construct a pixel coordinate system. Based on the pixel coordinate system, a preset length of , width is The winding thermal image is smoothed based on the pixel neighborhood and the smoothing formula is:

[0051] ;in, Represents the coordinates in the pixel coordinate system The smoothed pixel value of the pixel at Represents the horizontal axis value of the pixel coordinate system, Represents the vertical axis value of the pixel coordinate system, represents the length of the pixel neighborhood, represents the width of the pixel neighborhood, Represents the coordinates in the pixel coordinate system The pixel value of the pixel at Represents the standard deviation of the pixel values ​​in the winding thermal image, represents pi;

[0052] The winding thermal image is regionally enhanced based on the smoothed pixel value. The calculation formula for regional enhancement is: ;in, Represents the coordinates in the pixel coordinate system The enhanced pixel value of the pixel at Represents the coordinates in the pixel coordinate system The second-order derivative of the pixel point in the horizontal direction of the pixel coordinate system, Represents the coordinates in the pixel coordinate system The second-order derivative of the pixel point in the vertical direction of the pixel coordinate system;

[0053] Temperature conversion based on enhanced pixel value, formula for temperature conversion

[0054] ;in, Represents the coordinates in the pixel coordinate system The pixel temperature of the pixel at and represents the calibration constant (obtained from the production parameters of the high-precision infrared thermal imager), Represents the material emissivity (obtained from the material parameters of the transformer winding). The emissivity of the object surface varies from material to material. The higher the emissivity, the more energy the object surface radiates.

[0055] The pixel temperature is corrected based on the ambient temperature. The temperature correction formula is:

[0056] ;in, Represents the coordinates in the pixel coordinate system The actual temperature of the pixel at Represents the ambient temperature;

[0057] The temperature threshold is preset, and hotspot detection is performed on the actual temperature based on the temperature threshold. The formula for hotspot detection is: ;in, Represents the hotspot labeling matrix, 1 represents a hotspot (i.e., an abnormal point), and 0 represents a non-hotspot (i.e., a normal point). represents the temperature threshold;

[0058] Based on the hotspot marking matrix, the hotspot temperature of the winding thermal image is marked to obtain the hotspot temperature distribution map. The formula for hotspot temperature marking is: ;in, Represents the coordinates in the pixel coordinate system The temperature value of the pixel at

[0059] The temperature information in the winding thermal image is effectively processed through pixel coordinate systems, smoothing, and area enhancement operations. In particular, the smoothing and enhancement of temperature data can better demonstrate local temperature changes in the winding, improving the accuracy of hotspot detection. The formula for detecting actual temperature based on temperature thresholds can effectively identify abnormal hotspot areas, ensuring the reliability and accuracy of detection.

[0060] A winding insulation aging prediction model is constructed based on the hotspot temperature distribution map and aging degree labels. The construction method of the winding insulation aging prediction model includes:

[0061] The winding insulation aging prediction model is a neural network model. It uses the hotspot temperature distribution map as input, the winding insulation aging degree as output, and the aging degree label as the prediction target for model training. The architecture of the winding insulation aging prediction model includes: convolution layer, pooling layer, and fully connected layer. The formula for defining the convolution operation of the winding insulation aging prediction model is: ;in, Representative The convolution kernel is located at the hotspot temperature distribution map. The convolution value at Represents the index of the long side pixel of the hotspot temperature distribution map, Represents the index of the wide edge pixel of the hotspot temperature distribution map, represents the index of the convolution kernel, Representative The weight matrix of the convolution kernel, and represents the index of the element position in the weight matrix, The representative hot spot temperature distribution diagram is at position The pixel value at Representative The bias term of the convolution kernel enables the model to learn more complex features. Represents the activation function, which is used to improve the performance of the model;

[0062] Through a neural network model, the convolutional, pooling, and fully connected layers are used to learn and extract the features of the hotspot temperature distribution map, achieving accurate prediction of the degree of winding insulation aging. This prediction method based on actual temperature distribution improves the system's adaptability and prediction accuracy in different environments.

[0063] The loss function of the winding insulation aging prediction model is defined as: ;in, represents the loss function value, Represents the total number of aging degree label categories, Represents the aging degree label category index, Represents the true distribution The probability of an aging degree label, Represents the first The probability of an aging level label;

[0064] The steps of obtaining the optimal winding insulation aging prediction model by minimizing the value of the loss function of the winding insulation aging prediction model include:

[0065] Step 1: Initialize E ants; initialize the parameter space of the winding insulation aging prediction model, which includes the weight matrix and bias term of the convolution kernel, and assign each ant to a different position in the parameter space; initialize pheromone: assign an initial pheromone concentration to each ant;

[0066] Step 2: Each ant moves in the parameter space and selects the direction of the next position to be updated based on the path probability. The calculation formula of the path probability is: ;in, Represents the ant from the position Select Path to Location The probability of Representative position To location Pheromones are chemical markers left by ants on their trails. The higher the concentration, the more attractive the trail. Pheromone weight coefficient, which controls the influence of pheromone on path selection. and represents the position index, and , Representative position The inverse of the loss function value of the winding insulation aging prediction model in the corresponding parameter space, Represents the index of the selected position (position indices of all locations where selections were made);

[0067] Step 3: After each ant selects a path, it updates its position and calculates the corresponding loss function value of each ant based on the parameters at the selected position through the loss function of the winding insulation aging prediction model. That is, each ant updates its current position selection based on the loss function value at each step;

[0068] Step 4: Update the pheromone concentration of the found path according to the loss function value corresponding to each ant. The formula for updating the pheromone concentration is:

[0069] ;in, Representative position To location The updated value of the pheromone concentration, Represents the pheromone volatility coefficient, which is used to simulate the natural volatility of pheromones. represents the index of the ant, Representative The loss function value of an ant, represents the total number of ants, represents a constant used to adjust the pheromone increment;

[0070] Step 5: When the maximum number of iterations is reached or the loss function of the winding insulation aging prediction model converges, the parameters corresponding to the locations where the largest number of ants gather are the parameter space that minimizes the loss function value of the winding insulation aging prediction model. If the maximum number of iterations is not reached and the loss function of the winding insulation aging prediction model has not converged, repeat steps 2, 3, and 4.

[0071] The ant colony algorithm was used to optimize the parameters of the winding insulation aging prediction model. The loss function was optimized through multiple rounds of iterations to ensure the effectiveness of parameter tuning. The ants' path selection and pheromone concentration update process simulated the intelligent search mechanism of biological groups, improving the model's convergence speed and optimization effect, thereby effectively enhancing the model's prediction accuracy.

[0072] Collect real-time transformer winding data, including real-time winding thermal images and real-time ambient temperature, and process the real-time transformer winding data accordingly to obtain hotspot temperature distribution maps.

[0073] The hotspot temperature distribution map is used as the input of the winding insulation aging prediction model to predict the degree of winding insulation aging. When the degree of winding insulation aging is moderate or severe, an alarm is triggered.

[0074] This embodiment performs hotspot detection and temperature marking on transformer winding data to better demonstrate local temperature changes in the winding, effectively identify abnormal hotspot areas, improve the accuracy of hotspot detection, and ensure the reliability and accuracy of detection; through the neural network model, accurate prediction of the degree of aging of the winding insulation is achieved, and the adaptability and prediction accuracy of the system in different environments are improved; through the ant colony algorithm to optimize the model parameters, the intelligent search mechanism of the biological population is simulated, the convergence speed and optimization effect of the model are improved, thereby effectively improving the prediction accuracy of the model; by accurately predicting the aging degree of the transformer winding, the initiative of transformer maintenance is greatly improved, helping users take necessary measures before a fault occurs, reducing the risk of power outages and equipment damage, and extending the service life of the equipment.

[0075] Example 2

[0076] See also Figure 2 As shown, for the parts not described in detail in this embodiment, please refer to the description of embodiment 1. A transformer winding insulation monitoring method is provided, including:

[0077] S1. Collect transformer winding data and aging degree labels;

[0078] S2. Perform image enhancement processing on the transformer winding data to generate enhanced winding image data; perform temperature conversion processing based on the enhanced winding image data, perform temperature correction based on the ambient temperature, and generate actual temperature data; perform hotspot detection and temperature marking based on the actual temperature data to generate a hotspot temperature distribution map;

[0079] S3. Constructing a winding insulation aging prediction model for predicting the degree of winding insulation aging based on the hotspot temperature distribution map and the aging degree label;

[0080] S4. Collect real-time transformer winding data, perform prediction based on the real-time transformer winding data through the winding insulation aging prediction model, obtain the degree of winding insulation aging, and make early warning judgments based on the degree of winding insulation aging.

[0081] Example 3

[0082] This embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the operation mode of the transformer winding insulation monitoring method provided above is implemented.

[0083] Since the electronic device described in this embodiment is an electronic device used to implement a transformer winding insulation monitoring method in the embodiment of the present application, based on the transformer winding insulation monitoring method described in the embodiment of the present application, those skilled in the art will be able to understand the specific implementation of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application will not be described in detail here. As long as those skilled in the art implement the electronic device used in the transformer winding insulation monitoring method in the embodiment of the present application, it falls within the scope of protection of this application.

[0084] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters and thresholds in the formulas are set by technicians in this field according to actual conditions.

[0085] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiment. All technical solutions based on the principles of the present invention are within the scope of protection of the present invention. It should be noted that for users of ordinary skill in the art, various improvements and modifications that do not depart from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A transformer winding insulation monitoring system, characterized in that: include: Data acquisition module: collects transformer winding data and aging degree labels; Data processing module: performs image enhancement processing on transformer winding data to generate enhanced winding image data, performs temperature conversion processing based on the enhanced winding image data, performs temperature correction based on the ambient temperature, and generates actual temperature data; Perform hotspot detection and temperature marking based on actual temperature data to generate a hotspot temperature distribution map; Model building module: Builds a winding insulation aging prediction model based on the hotspot temperature distribution map and aging degree labels to predict the degree of winding insulation aging; Real-time detection module: collects real-time transformer winding data, uses the winding insulation aging prediction model to predict the degree of winding insulation aging based on the real-time transformer winding data, and makes early warning judgments based on the degree of winding insulation aging; The method of performing image enhancement processing on transformer winding data includes: The upper left corner of the winding thermal image is used as the coordinate origin, and the number of pixels of the length and width of the winding thermal image is used as the coordinate axis scale to construct a pixel coordinate system. Based on the pixel coordinate system, a preset length of , width is The winding thermal image is smoothed based on the pixel neighborhood. The smoothing formula is: ;in, Represents the coordinates in the pixel coordinate system The smoothed pixel value of the pixel at Represents the horizontal axis value of the pixel coordinate system, Represents the vertical axis value of the pixel coordinate system, represents the length of the pixel neighborhood, represents the width of the pixel neighborhood, Represents the coordinates in the pixel coordinate system The pixel value of the pixel at Represents the standard deviation of the pixel values ​​in the winding thermal image, represents pi; The winding thermal image is regionally enhanced based on the smoothed pixel value. The calculation formula for regional enhancement is: ;in, Represents the coordinates in the pixel coordinate system The enhanced pixel value of the pixel at Represents the coordinates in the pixel coordinate system The second-order derivative of the pixel point in the horizontal direction of the pixel coordinate system, Represents the coordinates in the pixel coordinate system The second-order derivative of the pixel point in the vertical direction of the pixel coordinate system; The method of generating actual temperature data includes: The temperature conversion is performed based on the enhanced pixel value. The formula for temperature conversion is: ;in, Represents the coordinates in the pixel coordinate system The pixel temperature of the pixel at and represents the calibration constant, represents the material emissivity; The pixel temperature is corrected based on the ambient temperature. The temperature correction formula is: ;in, Represents the coordinates in the pixel coordinate system The actual temperature of the pixel at Represents the ambient temperature.

2. A transformer winding insulation monitoring system according to claim 1, characterized in that: The transformer winding data includes: winding thermal image and ambient temperature; aging degree labels include: normal, slightly aged, moderately aged and severely aged.

3. A transformer winding insulation monitoring system according to claim 2, characterized in that: The method of generating the hotspot temperature distribution map includes: The temperature threshold is preset, and hotspot detection is performed on the actual temperature based on the temperature threshold. The formula for hotspot detection is: ;in, Represents the hotspot labeling matrix, 1 represents a hotspot, 0 represents a non-hotspot, represents the temperature threshold; Based on the hotspot marking matrix, the hotspot temperature of the winding thermal image is marked to obtain the hotspot temperature distribution map. The formula for hotspot temperature marking is: ;in, Represents the coordinates in the pixel coordinate system The temperature value of the pixel.

4. A transformer winding insulation monitoring system according to claim 3, characterized in that: The method for constructing the winding insulation aging prediction model includes: The winding insulation aging prediction model is defined, and the defined winding insulation aging prediction model is trained and tuned through the optimization algorithm to obtain the optimal winding insulation aging prediction model.

5. The transformer winding insulation monitoring system according to claim 4, characterized in that: The method of defining the model includes: The winding insulation aging prediction model is a neural network model. It uses the hotspot temperature distribution map as input, the winding insulation aging degree as output, and the aging degree label as the prediction target for model training. The architecture of the winding insulation aging prediction model includes: convolution layer, pooling layer, and fully connected layer. The formula for defining the convolution operation of the winding insulation aging prediction model is: ;in, Representative The convolution kernel is located at the hotspot temperature distribution map. The convolution value at Represents the index of the long side pixel of the hotspot temperature distribution map, Represents the index of the wide edge pixel of the hotspot temperature distribution map, represents the index of the convolution kernel, Representative The weight matrix of the convolution kernel, and represents the index of the element position in the weight matrix, The representative hot spot temperature distribution diagram is at position The pixel value at Representative The bias term of the convolution kernel, represents the activation function; The loss function of the winding insulation aging prediction model is defined as: ;in, represents the loss function value, Represents the total number of aging degree label categories, Represents the aging degree label category index, Represents the true distribution The probability of an aging degree label, Represents the first The probability of an aging degree label.

6. The transformer winding insulation monitoring system according to claim 5, characterized in that: The steps of performing training and tuning include: Step 1: Initialize E ants; initialize the parameter space of the winding insulation aging prediction model, which includes the weight matrix and bias term of the convolution kernel, and assign each ant to a different position in the parameter space; initialize pheromone: assign an initial pheromone concentration to each ant; Step 2: Each ant moves in the parameter space and selects the direction of the next position to be updated based on the path probability. The calculation formula of the path probability is: ;in, Represents the ant from the position Select Path to Location The probability of Representative position To location The pheromone concentration, Pheromone weight coefficient, and represents the position index, and , Representative position The inverse of the loss function value of the winding insulation aging prediction model in the corresponding parameter space, The index representing the selected position; Step 3: After each ant selects a path, it updates its position and calculates the loss function value corresponding to each ant based on the parameters at the selected position through the loss function of the winding insulation aging prediction model; Step 4: Update the pheromone concentration of the found path according to the loss function value corresponding to each ant. The formula for updating the pheromone concentration is: ;in, Representative position To location The updated value of the pheromone concentration, represents the pheromone volatility coefficient, represents the index of the ant, Representative The loss function value of an ant, represents the total number of ants, represents a constant; Step 5: When the maximum number of iterations is reached or the loss function of the winding insulation aging prediction model converges, the parameters corresponding to the locations where the largest number of ants gather are the parameter space that minimizes the loss function value of the winding insulation aging prediction model. When the maximum number of iterations is not reached and the loss function of the winding insulation aging prediction model has not converged, repeat steps 2, 3, and 4.

7. The transformer winding insulation monitoring system according to claim 6, characterized in that: The method of performing early warning judgment according to the degree of winding insulation aging includes: Collect real-time transformer winding data, including real-time winding thermal images and real-time ambient temperature. Process the real-time transformer winding data accordingly to obtain a hotspot temperature distribution map. Use the hotspot temperature distribution map as input for the winding insulation aging prediction model to predict the degree of winding insulation aging. Activate an alarm when the winding insulation aging degree is moderate or severe.

Images